Cover image
Try Now
2025-04-14

3 years

Works with Finder

0

Github Watches

0

Github Forks

0

Github Stars

Build an AI Agent that acts as an MCP Client

An example of how to build an Agent that acts as an MCP Client, so that it can connect to external services via MCP.

Deploy to Cloudflare

This demo showcases how to:

  • Connect an AI agent to a remote MCP server
  • Handle authentication check using the built-in OAuth flow
  • Discover and use tools exposed by remote MCP servers

Learn more

Instructions

First, start an MCP server. A simple example can be found in examples/mcp, which already has valid binding setup.

npm install
npm start

Tap "O + enter" to open the front end. It should list out all the tools, prompts, and resources available.

相关推荐

  • av
  • Exécutez sans effort LLM Backends, API, Frontends et Services avec une seule commande.

  • 1Panel-dev
  • 🔥 1Panel fournit une interface Web intuitive et un serveur MCP pour gérer des sites Web, des fichiers, des conteneurs, des bases de données et des LLM sur un serveur Linux.

  • rulego
  • ⛓️RULEGO est un cadre de moteur de règle d'orchestration des composants de nouvelle génération légère, intégrée, intégrée et de nouvelle génération pour GO.

  • WangRongsheng
  • 🧑‍🚀 全世界最好的 LLM 资料总结 (数据处理、模型训练、模型部署、 O1 模型、 MCP 、小语言模型、视觉语言模型) | Résumé des meilleures ressources LLM du monde.

  • Byaidu
  • PDF Traduction de papier scientifique avec formats conservés - 基于 AI 完整保留排版的 PDF 文档全文双语翻译 , 支持 Google / Deepl / Olllama / Openai 等服务 , 提供 CLI / GUI / MCP / DOCKER / ZOTERO

  • hkr04
  • SDK C ++ MCP (Protocole de contexte modèle léger)

  • sigoden
  • Créez facilement des outils et des agents LLM à l'aide de fonctions Plain Bash / JavaScript / Python.

  • RockChinQ
  • 😎简单易用、🧩丰富生态 - 大模型原生即时通信机器人平台 | 适配 QQ / 微信 (企业微信、个人微信) / 飞书 / 钉钉 / Discord / Telegram / Slack 等平台 | 支持 Chatgpt 、 Deepseek 、 Dify 、 Claude 、 GEMINI 、 XAI 、 PPIO 、 OLLAMA 、 LM Studio 、阿里云百炼、火山方舟、 Siliconflow 、 Qwen 、 Moonshot 、 ChatGlm 、 Sillytraven 、 MCP 等 LLM 的机器人 / Agent | Plateforme de bots de messagerie instantanée basés sur LLM, prend en charge Discord, Telegram, WeChat, Lark, Dingtalk, QQ, Slack

  • modelscope
  • Commencez à construire des applications multi-agents LLM, plus facilement.

  • dmayboroda
  • Rag de conversation sur site avec des conteneurs configurables

    Reviews

    3.6 (5)
    Avatar
    user_lpDfJ87V
    2025-04-24

    I recently tried the mcp-client-demo by shivankgoel, and I must say it is incredibly impressive. The client is intuitive and easy to use, making it perfect for both beginners and experienced users. The step-by-step guidance with clear welcome information ensured a smooth start. If you need a reliable client, this demo is a must-try!

    Avatar
    user_jdcVWX0J
    2025-04-24

    I recently tried out mcp-client-demo by shivankgoel and was thoroughly impressed. The application is seamless, easy to navigate, and provides a straightforward client demo experience. Although it's still a demo, it has great potential for further development. I'm excited to see where this project will go next! Highly recommend giving it a try.

    Avatar
    user_1VFjp7oo
    2025-04-24

    I've been using the mcp-client-demo created by shivankgoel, and it has truly impressed me. It's a versatile tool that simplifies client interactions, making the whole process seamless. The interface is user-friendly, and the onboarding instructions are straightforward, ensuring a smooth start. Highly recommend it for anyone looking to enhance their client management experience!

    Avatar
    user_uch1LRJK
    2025-04-24

    I've been using mcp-client-demo by shivankgoel and it's been a game-changer. The user-friendly interface and seamless integration make it a must-have for any developer. The setup was straightforward, and the documentation provided all the necessary details to get started quickly. Highly recommend!

    Avatar
    user_LrxgGk1p
    2025-04-24

    I recently started using the mcp-client-demo by shivankgoel and it has significantly improved my workflow. The interface is user-friendly and the initial setup was a breeze. It integrates seamlessly with my current projects, making development smoother and more efficient. Highly recommend this for any developer looking to enhance their productivity!